ATLASAML.T0051.000
ATLAS index
AML.T0051.000

Direct

An adversary may inject prompts directly as a user of the LLM. This type of injection may be used by the adversary to gain a foothold in the system or to misuse the LLM itself, as for example to generate harmful content.

Framework
MITRE ATLAS
Maturity
Realized
Platforms
Generative AI, Agentic AI
Release
2026.05

Overview

An adversary may inject prompts directly as a user of the LLM. This type of injection may be used by the adversary to gain a foothold in the system or to misuse the LLM itself, as for example to generate harmful content.

Sources

  1. MITRE ATLAS AML.T0051.000: Direct — MITRE